Delving into Out-of-Distribution Detection with Vision-Language Representations

• URL: http://arxiv.org/abs/2211.13445v1
• Date: Thu, 24 Nov 2022 07:12:51 GMT
• Title: Delving into Out-of-Distribution Detection with Vision-Language Representations
• Abstract summary: Maximum Concept Matching (MCM) is a zero-shot OOD detection method based on aligning visual features with textual concepts. We contribute in-depth analysis and theoretical insights to understand the effectiveness of MCM. MCM with vision-language features outperforms a common baseline with pure visual features on a hard OOD task with semantically similar classes by 13.1%.
• Score: 27.908755548309646
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recognizing out-of-distribution (OOD) samples is critical for machine learning systems deployed in the open world. The vast majority of OOD detection methods are driven by a single modality (e.g., either vision or language), leaving the rich information in multi-modal representations untapped. Inspired by the recent success of vision-language pre-training, this paper enriches the landscape of OOD detection from a single-modal to a multi-modal regime. Particularly, we propose Maximum Concept Matching (MCM), a simple yet effective zero-shot OOD detection method based on aligning visual features with textual concepts. We contribute in-depth analysis and theoretical insights to understand the effectiveness of MCM. Extensive experiments demonstrate that MCM achieves superior performance on a wide variety of real-world tasks. MCM with vision-language features outperforms a common baseline with pure visual features on a hard OOD task with semantically similar classes by 13.1% (AUROC). Code is available at https://github.com/deeplearning-wisc/MCM.

Related papers

• Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMs [80.03370593724422]
  Out-of-distribution (OOD) detection seeks to identify samples from unknown classes.<n>Current methods often incorporate intra-modal distance during OOD detection, such as comparing negative texts with ID labels.<n>We propose InterNeg, a framework that systematically utilizes consistent inter-modal distance enhancement from textual and visual perspectives.
  arXiv  Detail & Related papers  (2026-03-03T05:44:47Z)
• Vision Also You Need: Navigating Out-of-Distribution Detection with Multimodal Large Language Model [42.29540047339044]
  Out-of-Distribution (OOD) detection is a critical task that has garnered significant attention.<n>We propose a novel pipeline, MM-OOD, which leverages the multimodal reasoning capabilities of MLLMs.<n>Our method is designed to improve performance in both near and far OOD tasks.
  arXiv  Detail & Related papers  (2026-01-20T15:06:10Z)
• True Multimodal In-Context Learning Needs Attention to the Visual Context [69.63677595066012]
  Multimodal Large Language Models (MLLMs) have enabled Multimodal In-Context Learning (MICL)-adapting to new tasks.<n>Current MLLMs tend to neglect visual cues and over-rely on textual patterns, leading to mere text imitation rather than genuine multimodal adaptation.<n>We introduce Dynamic Attention Reallocation (DARA), an efficient fine-tuning strategy that encourages models to attend to the visual context.
  arXiv  Detail & Related papers  (2025-07-21T17:08:18Z)
• Advancing Multimodal Reasoning Capabilities of Multimodal Large Language Models via Visual Perception Reward [87.06604760273372]
  We propose Perception-R1, which introduces a novel visual perception reward that explicitly encourages MLLMs to perceive the visual content accurately.<n>We show that Perception-R1 achieves state-of-the-art performance on most benchmarks using only 1,442 training data.
  arXiv  Detail & Related papers  (2025-06-08T16:48:42Z)
• Active-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO [63.140883026848286]
  Active vision refers to the process of actively selecting where and how to look in order to gather task-relevant information.<n>Recently, the use of Multimodal Large Language Models (MLLMs) as central planning and decision-making modules in robotic systems has gained extensive attention.
  arXiv  Detail & Related papers  (2025-05-27T17:29:31Z)
• Instruction-Guided Fusion of Multi-Layer Visual Features in Large Vision-Language Models [50.98559225639266]
  We investigate the contributions of visual features from different encoder layers using 18 benchmarks spanning 6 task categories. Our findings reveal that multilayer features provide complementary strengths with varying task dependencies, and uniform fusion leads to suboptimal performance. We propose the instruction-guided vision aggregator, a module that dynamically integrates multi-layer visual features based on textual instructions.
  arXiv  Detail & Related papers  (2024-12-26T05:41:31Z)
• TagOOD: A Novel Approach to Out-of-Distribution Detection via Vision-Language Representations and Class Center Learning [26.446233594630087]
  We propose textbfTagOOD, a novel approach for OOD detection using vision-language representations. TagOOD trains a lightweight network on the extracted object features to learn representative class centers. These centers capture the central tendencies of IND object classes, minimizing the influence of irrelevant image features during OOD detection.
  arXiv  Detail & Related papers  (2024-08-28T06:37:59Z)
• A Concept-Based Explainability Framework for Large Multimodal Models [52.37626977572413]
  We propose a dictionary learning based approach, applied to the representation of tokens. We show that these concepts are well semantically grounded in both vision and text. We show that the extracted multimodal concepts are useful to interpret representations of test samples.
  arXiv  Detail & Related papers  (2024-06-12T10:48:53Z)
• MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities [11.884004583641325]
  We introduce the first-of-its-kind benchmark, MultiOOD, characterized by diverse dataset sizes and varying modality combinations. We first evaluate existing unimodal OOD detection algorithms on MultiOOD, observing that the mere inclusion of additional modalities yields substantial improvements. We introduce a novel outlier synthesis method, NP-Mix, which explores broader feature spaces by leveraging the information from nearest neighbor classes.
  arXiv  Detail & Related papers  (2024-05-27T17:59:02Z)
• Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models [87.47400128150032]
  We propose a novel LMM architecture named Lumen, a Large multimodal model with versatile vision-centric capability enhancement. Lumen first promotes fine-grained vision-language concept alignment. Then the task-specific decoding is carried out by flexibly routing the shared representation to lightweight task decoders.
  arXiv  Detail & Related papers  (2024-03-12T04:13:45Z)
• Behind the Magic, MERLIM: Multi-modal Evaluation Benchmark for Large Image-Language Models [50.653838482083614]
  This paper introduces a scalable test-bed to assess the capabilities of IT-LVLMs on fundamental computer vision tasks. MERLIM contains over 300K image-question pairs and has a strong focus on detecting cross-modal "hallucination" events in IT-LVLMs.
  arXiv  Detail & Related papers  (2023-12-03T16:39:36Z)
• u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model [17.3535277338312]
  u-LLaVA is an innovative unifying multi-task framework that integrates pixel, regional, and global features to refine the perceptual faculties of MLLMs. This work contributes a novel mask-based multi-task dataset comprising 277K samples, crafted to challenge and assess the fine-grained perception capabilities of MLLMs.
  arXiv  Detail & Related papers  (2023-11-09T13:18:27Z)
• Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection [67.68030805755679]
  Large language models (LLMs) encode a wealth of world knowledge and can be prompted to generate descriptive features for each class. In this paper, we propose to apply world knowledge to enhance OOD detection performance through selective generation from LLMs.
  arXiv  Detail & Related papers  (2023-10-12T04:14:28Z)
• General-Purpose Multi-Modal OOD Detection Framework [5.287829685181842]
  Out-of-distribution (OOD) detection identifies test samples that differ from the training data, which is critical to ensuring the safety and reliability of machine learning (ML) systems. We propose a general-purpose weakly-supervised OOD detection framework, called WOOD, that combines a binary classifier and a contrastive learning component. We evaluate the proposed WOOD model on multiple real-world datasets, and the experimental results demonstrate that the WOOD model outperforms the state-of-the-art methods for multi-modal OOD detection.
  arXiv  Detail & Related papers  (2023-07-24T18:50:49Z)
• OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models [122.27878464009181]
  We conducted a comprehensive evaluation of Large Multimodal Models, such as GPT4V and Gemini, in various text-related visual tasks. OCRBench contains 29 datasets, making it the most comprehensive OCR evaluation benchmark available.
  arXiv  Detail & Related papers  (2023-05-13T11:28:37Z)
• Tackling Visual Control via Multi-View Exploration Maximization [64.8463574294237]
  MEM is the first approach that combines multi-view representation learning and reward-driven exploration in reinforcement learning (RL) We evaluate MEM on various tasks from DeepMind Control Suite and Procgen games.
  arXiv  Detail & Related papers  (2022-11-28T11:29:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.